Skip to content

Conversation

wlemkows
Copy link
Contributor

No description provided.

@wlemkows
Copy link
Contributor Author

Unrelated issue:
Failed Tests (1):
Unified Runtime Conformance :: exp_usm_context_memcpy//exp_usm_context_memcpy-test/urUSMContextMemcpyExpTestDevice/Success/UR_BACKEND_CUDA__NVIDIA_CUDA_BACKEND__NVIDIA_A2_ID1ID_______z__3_Gb_______

Should be fixed by:
#19688

@@ -1462,6 +1353,143 @@ ur_result_t urDeviceGetInfo(
return UR_RESULT_SUCCESS;
}

ur_result_t urDeviceGet(
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This is hard to review because you moved the function. Can you move it back?

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Done.

// In case of DeviceType is DEFAULT, pick only the most powerful GPU
// device.
if (DeviceDefaultGPU) {
uint32_t maxComputeUnits = 0;
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

nit: I'm not sure if it wouldn't be cleaner to just collect matched devices here, and then outside this loop, if DeviceType == UR_DEVICE_TYPE_DEFAULT, iterate over them to select the best single GPU.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants